SADMA: Scalable Asynchronous Distributed Multi-Agent Reinforcement Learning Training Framework
Sizhe Wang*, Long Qian*, Cairun Yi,
Fan Wu, Qian Kou,
Mingyang Li, Xingyu Chen,Xuguang Lan†
*Equal contribution †Corresponding author
实验
吞吐量比较
我们比较了不同资源(单台和多台机器配置)下的基线。
收敛加速
我们比较了每个框架的收敛时间,使不同算法在相同的资源配置不同框架下收敛。
可扩展性评估
为了评估SADMA在大规模多智能体环境下的可扩展性,我们在CityFlow环境的基础上构建了一个包含1225个智能体的环境,以及一个包含1000个agent的物流环境。
Citation
@inproceedings{
wang2024SADMA,
title={SADMA: Scalable Asynchronous Distributed Multi-Agent Reinforcement Learning Training Framework},
author={Sizhe Wang, Long Qian, Cairun Yi, Fan Wu, Qian Kou, Mingyang Li, Xingyu Chen, Xuguang Lan},
booktitle={12th International Workshop on Engineering Multi-Agent Systems},
year={2024},
}
Wang, S., Qian, L., Yi, C., Wu, F., Kou, Q., Li, M., Chen, X., Lan, X.
SADMA: Scalable Asynchronous Distributed Multi-Agent Reinforcement Learning Training Framework.
In Proceedings of 12th International Workshop on Engineering Multi-Agent Systems Co-located with AAMAS 2024,
pages 31-47, Auckland, New Zealand, May. 2024. URLhttps://emas.in.tu-clausthal.de/2024/.